Repository navigation
fix(agent): detect non-consecutive tool call loops - #83
Closed
HamzaKhanBUIC wants to merge 1 commit into
Closed
HamzaKhanBUIC wants to merge 1 commit into
HamzaKhanBUIC wants to merge 1 commit into
Conversation
9 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes #72.
Enhances the duplicate tool call detector in Agent.run() to detect non-consecutive repeating cycles (e.g., A, B, A, B, A, B or A, B, C, A, B, C) and halt execution before consuming max_steps.
Problem
The detector only tracked the single immediately preceding tool signature (last_tool_signature). If an LLM alternated between two or more calls (e.g. calc(1), calc(2), calc(1), calc(2)), the consecutive counter was reset on every call, allowing the agent to spin endlessly until hitting max_steps.
Solution
aise_on_failure=True raises DuplicateToolCallLoopError with cycle_length.
Verification
uv run pytest tests/unit/test_agent_loop_detector.py-> 9/9 passeduv run ruff check .-> All checks passeduv run ruff format --check .-> 110 files already formatteduv run mypy agentkit tests/unit/test_agent_loop_detector.py-> Success: no issues found in 43 source files